Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 19-GEMMASCOPE-TRANSCODER-16K
    4. 10243
    Prev
    Next
    INDEX
    Explanations

    sentences about mythology and legends

    oai_token-act-pair · gemini-2.0-flash

    myths and legends

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     stránka
    -0.54
    XmlAccessorType
    -0.53
    PhysRevD
    -0.50
    tagHelperRunner
    -0.46
     '$
    -0.46
     initComponents
    -0.46
    IUrlHelper
    -0.44
    addContainerGap
    -0.43
    tvguidetime
    -0.42
     [$
    -0.42
    POSITIVE LOGITS
     legend
    1.69
     legends
    1.59
     myth
    1.48
     myths
    1.45
     Legend
    1.36
     mythology
    1.31
     LEGEND
    1.29
    legend
    1.28
     Myth
    1.26
     legenda
    1.25
    Activations Density 1.099%

    No Known Activations